© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 101873
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structural elements in code or data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Variable names, data types, and syntax elements in programming code across different languages, particularly focusing on function parameters, class members, and programming language constructs.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arşivlendi
    -0.50
     MainAxisSize
    -0.49
     <<<<<<<<<<<<<<
    -0.46
    ContentAsync
    -0.45
     betweenstory
    -0.44
     EconPapers
    -0.43
     Stoll
    -0.43
     imper
    -0.42
    %\[
    -0.41
    ตร์
    -0.41
    POSITIVE LOGITS
    afficheront
    0.56
    تقاوى
    0.45
     للاسماء
    0.40
     Autorizaciones
    0.39
    Hentet
    0.39
     surla
    0.38
    밌
    0.36
    Transcripción
    0.36
     ब्रेकडाउन
    0.36
     shadows
    0.35
    Activations Density 0.047%

    No Known Activations